1. The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge
- Author
-
Niu, Shutong, Wang, Ruoyu, Du, Jun, Yang, Gaobin, Tu, Yanhui, Wu, Siyuan, Qian, Shuangqing, Wu, Huaxin, Xu, Haitao, Zhang, Xueyang, Zhong, Guolong, Yu, Xindi, Chen, Jieru, Wang, Mengzhi, Cai, Di, Gao, Tian, Wan, Genshun, Ma, Feng, Pan, Jia, and Gao, Jianqing
- Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing ,Computer Science - Sound - Abstract
This technical report outlines our submission system for the CHiME-8 NOTSOFAR-1 Challenge. The primary difficulty of this challenge is the dataset recorded across various conference rooms, which captures real-world complexities such as high overlap rates, background noises, a variable number of speakers, and natural conversation styles. To address these issues, we optimized the system in several aspects: For front-end speech signal processing, we introduced a data-driven joint training method for diarization and separation (JDS) to enhance audio quality. Additionally, we also integrated traditional guided source separation (GSS) for multi-channel track to provide complementary information for the JDS. For back-end speech recognition, we enhanced Whisper with WavLM, ConvNeXt, and Transformer innovations, applying multi-task training and Noise KLD augmentation, to significantly advance ASR robustness and accuracy. Our system attained a Time-Constrained minimum Permutation Word Error Rate (tcpWER) of 14.265% and 22.989% on the CHiME-8 NOTSOFAR-1 Dev-set-2 multi-channel and single-channel tracks, respectively.
- Published
- 2024